
import scanpy as sc, anndata as ad, numpy as np, pandas as pd, seaborn as sns
from scipy import sparse
from anndata import AnnData
from matplotlib import pylab
import warnings
import scanpy.external as sce
import yaml
import matplotlib as plt
import os
import scvelo as scv

warnings.filterwarnings('ignore')


sc.settings.verbosity = 3             # verbosity: errors (0), warnings (1), info (2), hints (3)
sc.logging.print_header()
with open("../data/resources/rcParams.yaml") as f:
    rcParamsDict = yaml.full_load(f)
    for k in rcParamsDict["rcParams"]:
        print("{} {}".format(k,rcParamsDict["rcParams"][k]))
        plt.rcParams[k] = rcParamsDict["rcParams"][k]
    for k1 in set(list(rcParamsDict)).difference(set(["rcParams"])):
        print("{} {}".format(k1,rcParamsDict[k1]))

scanpy==1.8.0 anndata==0.8.0 umap==0.4.6 numpy==1.22.2 scipy==1.6.2 pandas==1.2.3 scikit-learn==0.24.1 statsmodels==0.13.5 python-igraph==0.9.1 louvain==0.7.0 leidenalg==0.8.3
figure.dpi 80
savefig.dpi 500
figure.figsize [10, 10]
axes.facecolor white
dotSize 20


outdir = "../data/output"

with open("../data/resources/iPSC_lines_map.yaml", 'r') as f:
    iPSC_lines_map = yaml.load(f, Loader=yaml.FullLoader)["lines"]

PoliudakisDSpath = "../data/resources/Poliudakis.h5ad"


PoliudakisAdata=sc.read_h5ad(PoliudakisDSpath )


sc.pl.umap(PoliudakisAdata, color="Cluster", size = 10,add_outline=True, outline_width=(0.2, 0.05), vmin='p2',vmax='p98',wspace=.4, frameon=False, save="poliudakis", legend_fontsize = "xx-large")

WARNING: saving figure to file figures/umappoliudakis.pdf


adataBU = sc.read_h5ad(outdir+"/adatas/ClusterAnnotated_Base_filt.h5ad")


adata = adataBU.copy()

PoliudakisAdata=sc.read_h5ad(PoliudakisDSpath )
PoliudakisAdata.var

adataIngestion = adata.copy()
#sc.pp.regress_out(adataIngestion, ["total_counts","pct_counts_mt"])

var_names = PoliudakisAdata.var_names.intersection(adataIngestion.var_names)
adataIngestion = adataIngestion[:, var_names].copy()
PoliudakisAdata = PoliudakisAdata[:, var_names].copy()
sc.tl.ingest(adataIngestion, PoliudakisAdata, obs='Cluster')



adataBU.obs["PoliudakisIngestedAnno"] = adataIngestion.obs.loc[adataBU.obs_names,"Cluster"]

del PoliudakisAdata

sc.pl.draw_graph(adataBU, size = 10, ncols=1, add_outline=True, color=["PoliudakisIngestedAnno"], wspace=.4)

running ingest
    finished (0:00:16)


for g in adataBU.obs["PoliudakisIngestedAnno"].unique():
    sc.pl.draw_graph(adataBU, groups=g, color="PoliudakisIngestedAnno", size = 10, 
               add_outline = True,outline_width=(0.4, 0.05),vmin="p1",vmax="p99", frameon=False, ncols=2,save="ingested."+g+".svg", na_color="#F5F5F5")

WARNING: saving figure to file figures/draw_graph_faingested.ExN.svg

WARNING: saving figure to file figures/draw_graph_faingested.InCGE.svg

WARNING: saving figure to file figures/draw_graph_faingested.OPC.svg

WARNING: saving figure to file figures/draw_graph_faingested.ExM.svg

WARNING: saving figure to file figures/draw_graph_faingested.oRG.svg

WARNING: saving figure to file figures/draw_graph_faingested.PgS.svg

WARNING: saving figure to file figures/draw_graph_faingested.IP.svg

WARNING: saving figure to file figures/draw_graph_faingested.vRG.svg

WARNING: saving figure to file figures/draw_graph_faingested.InMGE.svg

WARNING: saving figure to file figures/draw_graph_faingested.PgG2M.svg


atl100 = adataBU.obs["PoliudakisIngestedAnno"].value_counts()[adataBU.obs["PoliudakisIngestedAnno"].value_counts() > 100].index.tolist()
adataBUSS =  adataBU[adataBU.obs["PoliudakisIngestedAnno"].isin(atl100)]


import holoviews as hv
obsTupleToMap = ("leidenAnnotated","PoliudakisIngestedAnno")
SankeyDF=adataBUSS.obs[list(obsTupleToMap)]
SankeyDF.columns = ["leidenAnnotated","PoliudakisIngestedAnno"]
SankeyDF = SankeyDF.groupby(['leidenAnnotated','PoliudakisIngestedAnno']).size().reset_index().rename(columns={0:'count'})
SankeyDF=SankeyDF[SankeyDF["count"] != 0]
hv.extension('bokeh')



sankey1 = hv.Sankey(SankeyDF, kdims=["leidenAnnotated", "PoliudakisIngestedAnno"], vdims="count")



sankey1.opts(cmap='Colorblind',label_position='outer',
edge_color='leidenAnnotated', edge_line_width=0,
node_alpha=1.0, node_width=40, node_sort=True,
width=1100, height=700, bgcolor="white")


adataBU.obs["PoliudakisIngestedAnno_Projection"] = adataBU.obs["PoliudakisIngestedAnno"]
sc.pl.draw_graph(adataBU, size = 10, ncols=2, add_outline=True, color=["leidenAnnotated","PoliudakisIngestedAnno_Projection"], wspace=.6, save="ingested.pdf", frameon=False)

WARNING: saving figure to file figures/draw_graph_faingested.pdf


sc.pl.draw_graph(adata, color="cellID_newName", size = 10, 
               add_outline = True,outline_width=(0.2, 0.05),vmin="p1",vmax="p99", frameon=False, ncols=2)

Library loading¶

Configure paths¶

UMAP of Poliudakis DS¶

Import anndata_all¶

Ingestion on Gwschwind Amaia¶

Select ingested categories with at least 100 cells¶